{ "_name_or_path": "/net/storage149/autofs/css22/nwang/118/nvme1/nwang/hf_log/cache/hub/models--ibm-fms--Bamba-9.8b-1.8T-hf/snapshots/7f734e89c7fdd007dd7672074eb1d894eb6af4d5", "architectures": [ "BambaForCausalLM" ], "attention_dropout": 0.0, "attn_layer_indices": [ 9, 18, 27 ], "attn_rotary_emb": 64, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "mamba_chunk_size": 256, "mamba_conv_bias": true, "mamba_d_conv": 4, "mamba_d_head": 64, "mamba_d_state": 128, "mamba_dt_rank": 256, "mamba_expand": 2, "mamba_n_groups": 1, "mamba_n_heads": 128, "mamba_proj_bias": false, "model_type": "bamba", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_logits_to_keep": 1, "pad_token_id": 0, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "tensor", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "tensor", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": 1.3051470554436795, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "rms_norm_eps": 1e-05, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.47.0.dev0", "use_cache": true, "use_mamba_kernels": true, "vocab_size": 128256 }